From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934088AbXC0SGb (ORCPT ); Tue, 27 Mar 2007 14:06:31 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S934124AbXC0SGb (ORCPT ); Tue, 27 Mar 2007 14:06:31 -0400 Received: from smtp-out.google.com ([216.239.45.13]:50287 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934088AbXC0SGb (ORCPT ); Tue, 27 Mar 2007 14:06:31 -0400 DomainKey-Signature: a=rsa-sha1; s=beta; d=google.com; c=nofws; q=dns; h=received:message-id:date:from:to:subject:cc:in-reply-to: mime-version:content-type:content-transfer-encoding: content-disposition:references; b=ihee5A31dQiLe2SOS7OqljNlwj7eI8rhRSAl5fEuxjz77FUQpBKW1oWkX4SA71j22 5IHTtBl8nctTRTmEQnNgw== Message-ID: Date: Tue, 27 Mar 2007 11:06:24 -0700 From: "Ken Chen" To: "Andi Kleen" Subject: Re: [patch] cache pipe buf page address for non-highmem arch Cc: "Andrew Morton" , linux-kernel@vger.kernel.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On 27 Mar 2007 17:01:01 +0200, Andi Kleen wrote: > What is the problem? You have cache misses on the the hash table > or are the instructions really an issue on a modern CPU? It was page_to_pfn() on numa system. I think it's cache misses on per node pgdat lookup with node index calculation on each pipe buffer page. > e.g. i out of lined virt_to_page to save space, but it could be probably > inlined again if it was severly time critical. That would be a problem too, though not showing up in the pipe code path.